Back to Results
First PageMeta Content
Parallel computing / GPGPU / Classes of computers / Computer architecture / Video cards / BrookGPU / SIMD / Multi-core processor / CUDA / Computing / Computer hardware / Concurrent computing


Debunking the 100X GPU vs. CPU Myth: An Evaluation of Throughput Computing on CPU and GPU Victor W Lee† , Changkyu Kim† , Jatin Chhugani† , Michael Deisher† , Daehyun Kim† , Anthony D. Nguyen† , Nadathur Sati
Add to Reading List

Document Date: 2010-06-28 05:39:01


Open Document

File Size: 470,06 KB

Share Result on Facebook

City

Saint-Malo / New York / Washington / DC / Philadelphia / /

Company

GPU / Intel Corporation / IEEE Press / Nvidia / Amdahl / /

Country

France / United States / /

Currency

USD / /

/

Event

Reorganization / /

Facility

CUDA BLAS Library / CUDA CUFFT Library / SFU pipeline / /

IndustryTerm

similar throughput computing kernels / input search tree / search operation / throughput computing performance / non-graphic applications / synchronization solutions / medical imaging / platform-specific software optimization / graphics co-processor / software gather / important image processing algorithm / multi-banking / software optimization techniques / signal processing applications / transcendental hardware / throughput computing models / throughput computing architectures / graphics processing / important throughput computing kernels / important software optimization techniques / throughput computing processor / streaming applications / multi-core systems / large database management / index tree search / throughput computing processors / architecture processor / index search / finance / throughput computing characteristics / bank conflicts / computational finance / transcendental helps speedup throughput computing applications / throughput computing kernels / image processing kernels / conflict detection hardware / throughput computing applications / throughput kernels/applications / image processing purpose / Software prefetch instructions / memory technologies / graphics applications / platformspecific software optimizations / software optimizations / purpose computing / power management / fft algorithm / collision detection algorithm / multi-pass sorting algorithm / increased parallel processing / image processing / graphics processors / graphics hardware / linear algebra numerical algorithms / massive processing capability / parallel computing research / leverage high-end memory technology / multi-processor / graphics processor / mining / computing / caches and hardware / actual applications / throughput computing / multi-ported software-controlled 16KB memory / i7 processor / cache coherence protocol / on-chip / throughput computing workloads / i7 processors / throughput computing machines / /

MarketIndex

PARSEC / /

OperatingSystem

SUSE / Fermi / L3 / /

Organization

Society for Industrial and Applied Mathematics / Intel Corporation Computing Lab / IEEE Computer Society / /

Person

A. Nguyen / V / Constraint Solver / A. D. Nguyen / V / Mikhail Smelyanskiy / Victor W Lee / J. Xiong / S. Kumar / V / M. Murphy / V / Michael Deisher / T. Kaldewey / V / C. Kim / V / Pradeep Dubey / Ray Casting / N. Leischner / V / Anthony D. Nguyen / Srinivas Chennupaty / Per Hammarlund / /

Position

driver / Optimization General / GDDR memory controller / representative / memory controller / controller / programmer / B. Singer / /

Product

Franklin / /

ProgrammingLanguage

RC / DC / /

ProvinceOrState

New York / /

RadioStation

Core / /

Technology

Alpha / memory technologies / throughput computing processors / SMs / i7 processors / graphics co-processor / fft algorithm / graphics processors / throughput computing processor / multi-pass sorting algorithm / two processors / fluid dynamics / important image processing algorithm / linear algebra numerical algorithms / improved algorithm / FFT algorithms / operating system / GTX280 processor / shared memory / cache coherence protocol / image processing / i7 processor / throughput-oriented processors / pdf / encryption / memory technology / 1.3GHz GTX280 processor / GTX280 graphics processor / i7-960 processor / GTX280 processors / GJK collision detection algorithm / caching / architecture processor / DLP / simulation / DSP / parallel processing / Monte Carlo algorithms / medical imaging / /

URL

http /

SocialTag